6 papers
Terminal Dimension Reduction for Time Series with Applications
Alexander Munteanu, Matteo Russo, David Saulpic +1
Terminal embeddings have emerged as a powerful tool for dimension reduction. Given a set of points , a terminal embedding is a mapping $f:\mathbb{R}^d\righta…
Dimension Reduction for Curves: Simplified and Generalized
Matthijs Ebbens, Jie Lu, Alexander Munteanu
We revisit random projections for reducing the dimension of high-dimensional polygonal curves. Drawing from the toolbox of randomized linear algebra, we give a considerably simplif…
Optimal Dimension-Free Sampling for Regularized Classification
Meysam Alishahi, Alexander Munteanu, Simon Omlor +1
We prove optimal sampling bounds achieving -relative error for a broad class of Lipschitz continuous classification loss functions under various regularization t…
Scalable Learning of Multivariate Distributions via Coresets
Zeyu Ding, Katja Ickstadt, Nadja Klein +2
Efficient and scalable non-parametric or semi-parametric regression analysis and density estimation are of crucial importance to the fields of statistics and machine learning. Howe…
Hardness of High-Dimensional Linear Classification
Alexander Munteanu, Simon Omlor, Jeff M. Phillips
We establish new exponential in dimension lower bounds for the Maximum Halfspace Discrepancy problem, which models linear classification. Both are fundamental problems in computati…
Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
Amer Krivošija, Alexander Munteanu, André Nusser +1
This paper introduces -Dynamic Time Warping (-DTW), a novel dissimilarity measure for polygonal curves. -DTW has stronger metric properties than Dynamic Time Warping (DTW)…